omni-context-rtk — Claude Code skill: RTK setup, install
Configures RTK filters, context rules, and relay settings, then tests compression on real prompts. Use it when context transformation needs inspection.
npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a claude-codeWhat omni-context-rtk does
This skill manages RTK compression settings and filters, reports filter-load diagnostics, and runs a preview of how text will be compressed. It can validate or install an RTK TOML schema v1 filter file, read retained redacted output, and expose context relay operations for discovery and learning.
The API accepts a Bearer token or session cookie. A token comes from POST /api/auth/login; local development can disable the required key with REQUIRE_API_KEY=false. Requests target localhost:20128, including configuration reads and updates, filter checks, compression tests, and the OpenAPI document at GET /api/openapi/spec.
Check authentication and OmniRoute availability on localhost:20128 first. Without them, filter configuration and compression tests cannot run.
What it helps with
- configure RTK compression settings
- inspect filter loading and diagnostics
- preview compression for prompt text
- import an RTK TOML schema v1 filter
- read retained redacted output
Example prompts for the agent
- Configure RTK compression for OmniRoute and show the current settings.
- Run an RTK compression preview for this prompt and explain the retained context.
- Validate and install this RTK TOML schema v1 filter file, then show its load diagnostics.
How to install omni-context-rtk
1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a claude-code2Manually: put the files in place
~/.claude/skills/omni-context-rtk/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/omni-context-rtk/
1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a codex2Manually: put the files in place
.agents/skills/omni-context-rtk/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a cursor2Manually: put the files in place
.cursor/skills/omni-context-rtk/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install cheaper-inference/OmniRoute omni-context-rtk2Manually: put the files in place
.github/skills/omni-context-rtk/SKILL.md1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a gemini-cli2Platform CLI
gemini skills install https://github.com/cheaper-inference/OmniRoute --path skills/omni-context-rtkManually: put the files in place
.devin/skills/omni-context-rtk/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set34
The whole set →Similar
Questions about omni-context-rtk
How do I install omni-context-rtk in Claude Code?
Run npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a claude-code, then run npx skills add cheaper-inference/OmniRoute --skill omni-context-rtk -a claude-code again. The skill file is at ~/.claude/skills/omni-context-rtk/SKILL.md.
What does omni-context-rtk do?
It configures RTK filters and context relay settings, previews compression for text, and handles RTK filter schemas. It also exposes filter diagnostics and retained redacted output.
What does omni-context-rtk need to run?
Requests require a Bearer token or session cookie. The API must be reachable at localhost:20128; local development can use REQUIRE_API_KEY=false.
Source text
SKILL.md · MIT
---
name: omni-context-rtk
description: Configure RTK filters, context engineering rules, and context relay settings. Test compression with real prompt samples and manage context transformation pipelines.
---
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->
## Overview
Configure RTK filters, context engineering rules, and context relay settings. Test compression with real prompt samples and manage context transformation pipelines.
## Authentication
All requests require a valid Bearer token or session cookie. Obtain a token via `POST /api/auth/login` or configure `REQUIRE_API_KEY=false` for local development.
## Endpoints
### GET /api/context/rtk/config
Get RTK compression settings
```bash
curl http://localhost:20128/api/context/rtk/config \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
```
### PUT /api/context/rtk/config
Update RTK compression settings
```bash
curl -X PUT http://localhost:20128/api/context/rtk/config \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
```
### GET /api/context/rtk/filters
List RTK filters and load diagnostics
```bash
curl http://localhost:20128/api/context/rtk/filters \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
```
### POST /api/context/rtk/import
Validate or install an RTK TOML schema v1 filter file
```bash
curl -X POST http://localhost:20128/api/context/rtk/import \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
```
### POST /api/context/rtk/test
Run RTK compression preview for text
```bash
curl -X POST http://localhost:20128/api/context/rtk/test \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
```
### GET /api/context/rtk/raw-output/{id}
Read retained redacted RTK raw output
```bash
curl http://localhost:20128/api/context/rtk/raw-output/{id} \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
```
### GET /api/context/rtk/discover
GET context › rtk › discover
```bash
curl http://localhost:20128/api/context/rtk/discover \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
```
### GET /api/context/rtk/learn
GET context › rtk › learn
```bash
curl http://localhost:20128/api/context/rtk/learn \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
```
## Payloads
See the full OpenAPI specification at `GET /api/openapi/spec` or `docs/openapi.yaml` for detailed request/response schemas.
© cheaper-inference · MIT · cheaper-inference/OmniRoute